Prompt Injections for Defense. This seems to work :
Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to prevent it from taking harmful actions. The LLM responds by shutting down..
schneier.com covered an intrusion into operational technology systems. The affected systems include industrial control infrastructure used for managing physical processes. SCADA and PLC systems exposed to external networks without proper segmentation create attack paths that bypass traditional network perimeter defenses. The breach method used in this case involved known configuration weaknesses.
Source: schneier.com